Training in progress, step 6400
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:510fd68290d2e16621f50aea88bbfe1bbfb2151f0a2bd848ded06cfae14f2719
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:761fbe47b852d6c57c78536ba82acd2db302c413814888a4d6ffcacb4c506ae8
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f01efc875d93462731abdc8ba4543dc38687b79b452fb341dc32ab82403e416
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ce9410f256d7a93af2cd3618fb4d55eb6756e98f81582031ee1649e79739df
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1238,3 +1238,43 @@
|
|
| 1238 |
{"current_steps": 6190, "total_steps": 9625, "loss": 0.1678, "lr": 1.3621317972763981e-05, "epoch": 4.502000727537286, "percentage": 64.31, "elapsed_time": "1 day, 17:11:51", "remaining_time": "22:51:42"}
|
| 1239 |
{"current_steps": 6195, "total_steps": 9625, "loss": 0.1718, "lr": 1.3586953867502576e-05, "epoch": 4.505638413968716, "percentage": 64.36, "elapsed_time": "1 day, 17:14:49", "remaining_time": "22:50:14"}
|
| 1240 |
{"current_steps": 6200, "total_steps": 9625, "loss": 0.172, "lr": 1.3552610851807062e-05, "epoch": 4.509276100400146, "percentage": 64.42, "elapsed_time": "1 day, 17:17:52", "remaining_time": "22:48:49"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1238 |
{"current_steps": 6190, "total_steps": 9625, "loss": 0.1678, "lr": 1.3621317972763981e-05, "epoch": 4.502000727537286, "percentage": 64.31, "elapsed_time": "1 day, 17:11:51", "remaining_time": "22:51:42"}
|
| 1239 |
{"current_steps": 6195, "total_steps": 9625, "loss": 0.1718, "lr": 1.3586953867502576e-05, "epoch": 4.505638413968716, "percentage": 64.36, "elapsed_time": "1 day, 17:14:49", "remaining_time": "22:50:14"}
|
| 1240 |
{"current_steps": 6200, "total_steps": 9625, "loss": 0.172, "lr": 1.3552610851807062e-05, "epoch": 4.509276100400146, "percentage": 64.42, "elapsed_time": "1 day, 17:17:52", "remaining_time": "22:48:49"}
|
| 1241 |
+
{"current_steps": 6205, "total_steps": 9625, "loss": 0.1749, "lr": 1.3518289038615853e-05, "epoch": 4.512913786831575, "percentage": 64.47, "elapsed_time": "1 day, 17:21:55", "remaining_time": "22:47:57"}
|
| 1242 |
+
{"current_steps": 6210, "total_steps": 9625, "loss": 0.1702, "lr": 1.3483988540797652e-05, "epoch": 4.5165514732630045, "percentage": 64.52, "elapsed_time": "1 day, 17:24:37", "remaining_time": "22:46:20"}
|
| 1243 |
+
{"current_steps": 6215, "total_steps": 9625, "loss": 0.1691, "lr": 1.3449709471151051e-05, "epoch": 4.520189159694434, "percentage": 64.57, "elapsed_time": "1 day, 17:27:21", "remaining_time": "22:44:44"}
|
| 1244 |
+
{"current_steps": 6220, "total_steps": 9625, "loss": 0.1379, "lr": 1.3415451942404185e-05, "epoch": 4.523826846125864, "percentage": 64.62, "elapsed_time": "1 day, 17:29:20", "remaining_time": "22:42:43"}
|
| 1245 |
+
{"current_steps": 6225, "total_steps": 9625, "loss": 0.1718, "lr": 1.338121606721434e-05, "epoch": 4.5274645325572935, "percentage": 64.68, "elapsed_time": "1 day, 17:32:16", "remaining_time": "22:41:14"}
|
| 1246 |
+
{"current_steps": 6230, "total_steps": 9625, "loss": 0.1669, "lr": 1.334700195816761e-05, "epoch": 4.531102218988723, "percentage": 64.73, "elapsed_time": "1 day, 17:35:01", "remaining_time": "22:39:38"}
|
| 1247 |
+
{"current_steps": 6235, "total_steps": 9625, "loss": 0.1697, "lr": 1.3312809727778486e-05, "epoch": 4.534739905420153, "percentage": 64.78, "elapsed_time": "1 day, 17:37:49", "remaining_time": "22:38:04"}
|
| 1248 |
+
{"current_steps": 6240, "total_steps": 9625, "loss": 0.166, "lr": 1.3278639488489527e-05, "epoch": 4.5383775918515825, "percentage": 64.83, "elapsed_time": "1 day, 17:40:46", "remaining_time": "22:36:35"}
|
| 1249 |
+
{"current_steps": 6245, "total_steps": 9625, "loss": 0.1653, "lr": 1.3244491352670975e-05, "epoch": 4.542015278283012, "percentage": 64.88, "elapsed_time": "1 day, 17:43:44", "remaining_time": "22:35:06"}
|
| 1250 |
+
{"current_steps": 6250, "total_steps": 9625, "loss": 0.1733, "lr": 1.3210365432620371e-05, "epoch": 4.545652964714441, "percentage": 64.94, "elapsed_time": "1 day, 17:46:30", "remaining_time": "22:33:30"}
|
| 1251 |
+
{"current_steps": 6255, "total_steps": 9625, "loss": 0.1639, "lr": 1.3176261840562216e-05, "epoch": 4.5492906511458715, "percentage": 64.99, "elapsed_time": "1 day, 17:49:04", "remaining_time": "22:31:48"}
|
| 1252 |
+
{"current_steps": 6260, "total_steps": 9625, "loss": 0.138, "lr": 1.3142180688647574e-05, "epoch": 4.552928337577301, "percentage": 65.04, "elapsed_time": "1 day, 17:51:21", "remaining_time": "22:29:57"}
|
| 1253 |
+
{"current_steps": 6265, "total_steps": 9625, "loss": 0.1632, "lr": 1.3108122088953704e-05, "epoch": 4.55656602400873, "percentage": 65.09, "elapsed_time": "1 day, 17:54:19", "remaining_time": "22:28:27"}
|
| 1254 |
+
{"current_steps": 6270, "total_steps": 9625, "loss": 0.173, "lr": 1.3074086153483718e-05, "epoch": 4.56020371044016, "percentage": 65.14, "elapsed_time": "1 day, 17:57:12", "remaining_time": "22:26:55"}
|
| 1255 |
+
{"current_steps": 6275, "total_steps": 9625, "loss": 0.1652, "lr": 1.3040072994166186e-05, "epoch": 4.56384139687159, "percentage": 65.19, "elapsed_time": "1 day, 17:59:53", "remaining_time": "22:25:17"}
|
| 1256 |
+
{"current_steps": 6280, "total_steps": 9625, "loss": 0.162, "lr": 1.3006082722854786e-05, "epoch": 4.567479083303019, "percentage": 65.25, "elapsed_time": "1 day, 18:02:43", "remaining_time": "22:23:42"}
|
| 1257 |
+
{"current_steps": 6285, "total_steps": 9625, "loss": 0.1655, "lr": 1.2972115451327918e-05, "epoch": 4.571116769734449, "percentage": 65.3, "elapsed_time": "1 day, 18:05:31", "remaining_time": "22:22:07"}
|
| 1258 |
+
{"current_steps": 6290, "total_steps": 9625, "loss": 0.1871, "lr": 1.2938171291288359e-05, "epoch": 4.574754456165879, "percentage": 65.35, "elapsed_time": "1 day, 18:08:09", "remaining_time": "22:20:26"}
|
| 1259 |
+
{"current_steps": 6295, "total_steps": 9625, "loss": 0.2305, "lr": 1.2904250354362874e-05, "epoch": 4.578392142597308, "percentage": 65.4, "elapsed_time": "1 day, 18:10:28", "remaining_time": "22:18:35"}
|
| 1260 |
+
{"current_steps": 6300, "total_steps": 9625, "loss": 0.2265, "lr": 1.2870352752101841e-05, "epoch": 4.582029829028738, "percentage": 65.45, "elapsed_time": "1 day, 18:12:42", "remaining_time": "22:16:42"}
|
| 1261 |
+
{"current_steps": 6305, "total_steps": 9625, "loss": 0.2221, "lr": 1.283647859597894e-05, "epoch": 4.585667515460168, "percentage": 65.51, "elapsed_time": "1 day, 18:15:04", "remaining_time": "22:14:52"}
|
| 1262 |
+
{"current_steps": 6310, "total_steps": 9625, "loss": 0.2129, "lr": 1.2802627997390715e-05, "epoch": 4.589305201891597, "percentage": 65.56, "elapsed_time": "1 day, 18:17:23", "remaining_time": "22:13:01"}
|
| 1263 |
+
{"current_steps": 6315, "total_steps": 9625, "loss": 0.2339, "lr": 1.2768801067656258e-05, "epoch": 4.5929428883230266, "percentage": 65.61, "elapsed_time": "1 day, 18:19:44", "remaining_time": "22:11:12"}
|
| 1264 |
+
{"current_steps": 6320, "total_steps": 9625, "loss": 0.2135, "lr": 1.2734997918016818e-05, "epoch": 4.596580574754456, "percentage": 65.66, "elapsed_time": "1 day, 18:22:07", "remaining_time": "22:09:23"}
|
| 1265 |
+
{"current_steps": 6325, "total_steps": 9625, "loss": 0.2201, "lr": 1.2701218659635428e-05, "epoch": 4.600218261185885, "percentage": 65.71, "elapsed_time": "1 day, 18:24:28", "remaining_time": "22:07:33"}
|
| 1266 |
+
{"current_steps": 6330, "total_steps": 9625, "loss": 0.2175, "lr": 1.2667463403596592e-05, "epoch": 4.6038559476173155, "percentage": 65.77, "elapsed_time": "1 day, 18:26:38", "remaining_time": "22:05:37"}
|
| 1267 |
+
{"current_steps": 6335, "total_steps": 9625, "loss": 0.2295, "lr": 1.2633732260905836e-05, "epoch": 4.607493634048745, "percentage": 65.82, "elapsed_time": "1 day, 18:29:09", "remaining_time": "22:03:52"}
|
| 1268 |
+
{"current_steps": 6340, "total_steps": 9625, "loss": 0.2229, "lr": 1.2600025342489422e-05, "epoch": 4.611131320480174, "percentage": 65.87, "elapsed_time": "1 day, 18:31:19", "remaining_time": "22:01:56"}
|
| 1269 |
+
{"current_steps": 6345, "total_steps": 9625, "loss": 0.2132, "lr": 1.256634275919393e-05, "epoch": 4.6147690069116045, "percentage": 65.92, "elapsed_time": "1 day, 18:33:56", "remaining_time": "22:00:14"}
|
| 1270 |
+
{"current_steps": 6350, "total_steps": 9625, "loss": 0.2264, "lr": 1.2532684621785928e-05, "epoch": 4.618406693343034, "percentage": 65.97, "elapsed_time": "1 day, 18:36:05", "remaining_time": "21:58:18"}
|
| 1271 |
+
{"current_steps": 6355, "total_steps": 9625, "loss": 0.2173, "lr": 1.2499051040951585e-05, "epoch": 4.622044379774463, "percentage": 66.03, "elapsed_time": "1 day, 18:38:19", "remaining_time": "21:56:23"}
|
| 1272 |
+
{"current_steps": 6360, "total_steps": 9625, "loss": 0.2117, "lr": 1.2465442127296297e-05, "epoch": 4.6256820662058935, "percentage": 66.08, "elapsed_time": "1 day, 18:40:05", "remaining_time": "21:54:15"}
|
| 1273 |
+
{"current_steps": 6365, "total_steps": 9625, "loss": 0.2178, "lr": 1.2431857991344384e-05, "epoch": 4.629319752637323, "percentage": 66.13, "elapsed_time": "1 day, 18:41:44", "remaining_time": "21:52:03"}
|
| 1274 |
+
{"current_steps": 6370, "total_steps": 9625, "loss": 0.211, "lr": 1.2398298743538639e-05, "epoch": 4.632957439068752, "percentage": 66.18, "elapsed_time": "1 day, 18:43:24", "remaining_time": "21:49:52"}
|
| 1275 |
+
{"current_steps": 6375, "total_steps": 9625, "loss": 0.2163, "lr": 1.2364764494240036e-05, "epoch": 4.636595125500182, "percentage": 66.23, "elapsed_time": "1 day, 18:45:01", "remaining_time": "21:47:39"}
|
| 1276 |
+
{"current_steps": 6380, "total_steps": 9625, "loss": 0.2274, "lr": 1.2331255353727332e-05, "epoch": 4.640232811931612, "percentage": 66.29, "elapsed_time": "1 day, 18:46:38", "remaining_time": "21:45:26"}
|
| 1277 |
+
{"current_steps": 6385, "total_steps": 9625, "loss": 0.2185, "lr": 1.229777143219671e-05, "epoch": 4.643870498363041, "percentage": 66.34, "elapsed_time": "1 day, 18:48:18", "remaining_time": "21:43:15"}
|
| 1278 |
+
{"current_steps": 6390, "total_steps": 9625, "loss": 0.2173, "lr": 1.2264312839761434e-05, "epoch": 4.647508184794471, "percentage": 66.39, "elapsed_time": "1 day, 18:50:02", "remaining_time": "21:41:06"}
|
| 1279 |
+
{"current_steps": 6395, "total_steps": 9625, "loss": 0.2006, "lr": 1.2230879686451438e-05, "epoch": 4.6511458712259, "percentage": 66.44, "elapsed_time": "1 day, 18:51:44", "remaining_time": "21:38:56"}
|
| 1280 |
+
{"current_steps": 6400, "total_steps": 9625, "loss": 0.2086, "lr": 1.2197472082213048e-05, "epoch": 4.65478355765733, "percentage": 66.49, "elapsed_time": "1 day, 18:53:26", "remaining_time": "21:36:46"}
|